1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+m,+f,+d,+v -verify-machineinstrs < %s | FileCheck %s
define <vscale x 1 x double> @test_vp_reverse_nxv1f64_masked(<vscale x 1 x double> %src, <vscale x 1 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv1f64_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT: vid.v v9, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT: vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT: vmv.v.v v8, v9
; CHECK-NEXT: ret
%dst = call <vscale x 1 x double> @llvm.experimental.vp.reverse.nxv1f64(<vscale x 1 x double> %src, <vscale x 1 x i1> %mask, i32 %evl)
ret <vscale x 1 x double> %dst
}
define <vscale x 1 x double> @test_vp_reverse_nxv1f64(<vscale x 1 x double> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT: vid.v v9
; CHECK-NEXT: vrsub.vx v10, v9, a1
; CHECK-NEXT: vrgather.vv v9, v8, v10
; CHECK-NEXT: vmv.v.v v8, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 1 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> undef, <vscale x 1 x i32> zeroinitializer
%dst = call <vscale x 1 x double> @llvm.experimental.vp.reverse.nxv1f64(<vscale x 1 x double> %src, <vscale x 1 x i1> %allones, i32 %evl)
ret <vscale x 1 x double> %dst
}
define <vscale x 2 x float> @test_vp_reverse_nxv2f32_masked(<vscale x 2 x float> %src, <vscale x 2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2f32_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT: vid.v v9, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT: vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT: vmv.v.v v8, v9
; CHECK-NEXT: ret
%dst = call <vscale x 2 x float> @llvm.experimental.vp.reverse.nxv2f32(<vscale x 2 x float> %src, <vscale x 2 x i1> %mask, i32 %evl)
ret <vscale x 2 x float> %dst
}
define <vscale x 2 x float> @test_vp_reverse_nxv2f32(<vscale x 2 x float> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT: vid.v v9
; CHECK-NEXT: vrsub.vx v10, v9, a1
; CHECK-NEXT: vrgather.vv v9, v8, v10
; CHECK-NEXT: vmv.v.v v8, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 2 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
%dst = call <vscale x 2 x float> @llvm.experimental.vp.reverse.nxv2f32(<vscale x 2 x float> %src, <vscale x 2 x i1> %allones, i32 %evl)
ret <vscale x 2 x float> %dst
}
define <vscale x 2 x double> @test_vp_reverse_nxv2f64_masked(<vscale x 2 x double> %src, <vscale x 2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2f64_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT: vid.v v10, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v12, v10, a0, v0.t
; CHECK-NEXT: vrgather.vv v10, v8, v12, v0.t
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: ret
%dst = call <vscale x 2 x double> @llvm.experimental.vp.reverse.nxv2f64(<vscale x 2 x double> %src, <vscale x 2 x i1> %mask, i32 %evl)
ret <vscale x 2 x double> %dst
}
define <vscale x 2 x double> @test_vp_reverse_nxv2f64(<vscale x 2 x double> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT: vid.v v10
; CHECK-NEXT: vrsub.vx v12, v10, a1
; CHECK-NEXT: vrgather.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: ret
%head = insertelement <vscale x 2 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
%dst = call <vscale x 2 x double> @llvm.experimental.vp.reverse.nxv2f64(<vscale x 2 x double> %src, <vscale x 2 x i1> %allones, i32 %evl)
ret <vscale x 2 x double> %dst
}
define <vscale x 4 x float> @test_vp_reverse_nxv4f32_masked(<vscale x 4 x float> %src, <vscale x 4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4f32_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vid.v v10, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v12, v10, a0, v0.t
; CHECK-NEXT: vrgather.vv v10, v8, v12, v0.t
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: ret
%dst = call <vscale x 4 x float> @llvm.experimental.vp.reverse.nxv4f32(<vscale x 4 x float> %src, <vscale x 4 x i1> %mask, i32 %evl)
ret <vscale x 4 x float> %dst
}
define <vscale x 4 x float> @test_vp_reverse_nxv4f32(<vscale x 4 x float> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT: vid.v v10
; CHECK-NEXT: vrsub.vx v12, v10, a1
; CHECK-NEXT: vrgather.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: ret
%head = insertelement <vscale x 4 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
%dst = call <vscale x 4 x float> @llvm.experimental.vp.reverse.nxv4f32(<vscale x 4 x float> %src, <vscale x 4 x i1> %allones, i32 %evl)
ret <vscale x 4 x float> %dst
}
define <vscale x 4 x double> @test_vp_reverse_nxv4f64_masked(<vscale x 4 x double> %src, <vscale x 4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4f64_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vid.v v12, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v16, v12, a0, v0.t
; CHECK-NEXT: vrgather.vv v12, v8, v16, v0.t
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: ret
%dst = call <vscale x 4 x double> @llvm.experimental.vp.reverse.nxv4f64(<vscale x 4 x double> %src, <vscale x 4 x i1> %mask, i32 %evl)
ret <vscale x 4 x double> %dst
}
define <vscale x 4 x double> @test_vp_reverse_nxv4f64(<vscale x 4 x double> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT: vid.v v12
; CHECK-NEXT: vrsub.vx v16, v12, a1
; CHECK-NEXT: vrgather.vv v12, v8, v16
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: ret
%head = insertelement <vscale x 4 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
%dst = call <vscale x 4 x double> @llvm.experimental.vp.reverse.nxv4f64(<vscale x 4 x double> %src, <vscale x 4 x i1> %allones, i32 %evl)
ret <vscale x 4 x double> %dst
}
define <vscale x 8 x float> @test_vp_reverse_nxv8f32_masked(<vscale x 8 x float> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8f32_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT: vid.v v12, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v16, v12, a0, v0.t
; CHECK-NEXT: vrgather.vv v12, v8, v16, v0.t
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: ret
%dst = call <vscale x 8 x float> @llvm.experimental.vp.reverse.nxv8f32(<vscale x 8 x float> %src, <vscale x 8 x i1> %mask, i32 %evl)
ret <vscale x 8 x float> %dst
}
define <vscale x 8 x float> @test_vp_reverse_nxv8f32(<vscale x 8 x float> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8f32:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT: vid.v v12
; CHECK-NEXT: vrsub.vx v16, v12, a1
; CHECK-NEXT: vrgather.vv v12, v8, v16
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: ret
%head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
%dst = call <vscale x 8 x float> @llvm.experimental.vp.reverse.nxv8f32(<vscale x 8 x float> %src, <vscale x 8 x i1> %allones, i32 %evl)
ret <vscale x 8 x float> %dst
}
define <vscale x 8 x double> @test_vp_reverse_nxv8f64_masked(<vscale x 8 x double> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8f64_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vid.v v16, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v24, v16, a0, v0.t
; CHECK-NEXT: vrgather.vv v16, v8, v24, v0.t
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: ret
%dst = call <vscale x 8 x double> @llvm.experimental.vp.reverse.nxv8f64(<vscale x 8 x double> %src, <vscale x 8 x i1> %mask, i32 %evl)
ret <vscale x 8 x double> %dst
}
define <vscale x 8 x double> @test_vp_reverse_nxv8f64(<vscale x 8 x double> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8f64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vid.v v16
; CHECK-NEXT: vrsub.vx v24, v16, a1
; CHECK-NEXT: vrgather.vv v16, v8, v24
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: ret
%head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
%dst = call <vscale x 8 x double> @llvm.experimental.vp.reverse.nxv8f64(<vscale x 8 x double> %src, <vscale x 8 x i1> %allones, i32 %evl)
ret <vscale x 8 x double> %dst
}
define <vscale x 16 x float> @test_vp_reverse_nxv16f32_masked(<vscale x 16 x float> %src, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16f32_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT: vid.v v16, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v24, v16, a0, v0.t
; CHECK-NEXT: vrgather.vv v16, v8, v24, v0.t
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: ret
%dst = call <vscale x 16 x float> @llvm.experimental.vp.reverse.nxv16f32(<vscale x 16 x float> %src, <vscale x 16 x i1> %mask, i32 %evl)
ret <vscale x 16 x float> %dst
}
define <vscale x 16 x float> @test_vp_reverse_nxv16f32(<vscale x 16 x float> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16f32:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT: vid.v v16
; CHECK-NEXT: vrsub.vx v24, v16, a1
; CHECK-NEXT: vrgather.vv v16, v8, v24
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: ret
%head = insertelement <vscale x 16 x i1> undef, i1 1, i32 0
%allones = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
%dst = call <vscale x 16 x float> @llvm.experimental.vp.reverse.nxv16f32(<vscale x 16 x float> %src, <vscale x 16 x i1> %allones, i32 %evl)
ret <vscale x 16 x float> %dst
}
; LMUL = 1
declare <vscale x 1 x double> @llvm.experimental.vp.reverse.nxv1f64(<vscale x 1 x double>,<vscale x 1 x i1>,i32)
declare <vscale x 2 x float> @llvm.experimental.vp.reverse.nxv2f32(<vscale x 2 x float>,<vscale x 2 x i1>,i32)
; LMUL = 2
declare <vscale x 2 x double> @llvm.experimental.vp.reverse.nxv2f64(<vscale x 2 x double>,<vscale x 2 x i1>,i32)
declare <vscale x 4 x float> @llvm.experimental.vp.reverse.nxv4f32(<vscale x 4 x float>,<vscale x 4 x i1>,i32)
; LMUL = 4
declare <vscale x 4 x double> @llvm.experimental.vp.reverse.nxv4f64(<vscale x 4 x double>,<vscale x 4 x i1>,i32)
declare <vscale x 8 x float> @llvm.experimental.vp.reverse.nxv8f32(<vscale x 8 x float>,<vscale x 8 x i1>,i32)
; LMUL = 8
declare <vscale x 8 x double> @llvm.experimental.vp.reverse.nxv8f64(<vscale x 8 x double>,<vscale x 8 x i1>,i32)
declare <vscale x 16 x float> @llvm.experimental.vp.reverse.nxv16f32(<vscale x 16 x float>,<vscale x 16 x i1>,i32)
|
